Qwen3.5 Claude Coder — local coding agents A family of custom models built on **Qwen3.5**, tuned to act as **autonomous coding and administration agents**.
2,107 Pulls 2 Tags Updated 1 week ago
Q8_0 Coder Claude-4.6-Opus
34.2K Pulls 5 Tags Updated 2 months ago
Coding-optimized variants of the official Qwen3.5 MoE models — full vision capability retained, tuned for precise code generation via lower temperature. Based on Alibaba's Qwen3.5 distributed through the Ollama registry.
9,233 Pulls 2 Tags Updated 2 months ago
Q4_K_M Coder Claude-4.6-Opus
7,902 Pulls 5 Tags Updated 2 months ago
Qwen3.5-27B Q4_K_M/Q5_K_M/Q8_0 Coder Claude-4.6-Opus, All models have been tested!
3,522 Pulls 3 Tags Updated 2 months ago
294 Pulls 1 Tag Updated 3 months ago
Qwen3.5 model (27B dense) with always-on thinking, optimized for agentic coding, tool use, and browser automation.
1,405 Pulls 4 Tags Updated 3 months ago
🌐 Sovereign Qwen3.5 text, code, JP. Vision support at https://huggingface.co/FieldMouse-AI ・ 🇯🇵 Qwen3.5 テキスト・コード・日本語対応。画像認識は https://huggingface.co/FieldMouse-AI で利用可能です。
1,131 Pulls 228 Tags Updated 2 months ago
Non-thinking qwen3.5:4b tuned for concise conversational chat with verbatim short code preservation.
256 Pulls 1 Tag Updated 1 month ago
qwen3-coder with tools calling, context 58k to match full memory 31GB on RTX5090
558 Pulls 1 Tag Updated 10 months ago
A coding-optimized configuration of Qwen3.5-9B designed for 16 GB single-GPU hardware. The model uses the official Q4_K_M quantization (~6.6 GB weights), leaving ~9 GB headroom for KV cache — enabling 32K+ context windows comfortably.
96 Pulls 1 Tag Updated 2 days ago
26.3.7. Qwen3.5-9B-Q4 Update: This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.
23.8K Pulls 1 Tag Updated 3 months ago
26.3.7. Qwen3.5-27B-Q4 Update: This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.
10.8K Pulls 1 Tag Updated 3 months ago
mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-heretic-GGUF
3,697 Pulls 2 Tags Updated 2 months ago
26.3.7. Update: This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.
1,321 Pulls 1 Tag Updated 3 months ago
Fully decensored Qwen2.5-Coder-3B-Instruct processed with Heretic abliteration. Achieves 3/100 refusals with an exceptionally low KL divergence of 0.0163 — near-zero model degradation on a consumer RTX 4060.
828 Pulls 1 Tag Updated 3 weeks ago
872 Pulls 1 Tag Updated 3 months ago
A Custom Qwen2.5-coder:3b-instruct using a Qwen2.5-coder:1.5b model as speculative fill. Primary usage for this model is TabbyML.
97 Pulls 1 Tag Updated 1 month ago
This model aims to combine the reasoning, code, and math capabilities of Qwen3 4b 2507 reasoning by merging it with some Qwen3 4b finetunes. This model reasoning is very long.
263 Pulls 4 Tags Updated 8 months ago
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models available in [F16, q8_0, q6_K, q4_K_S]
3,799 Pulls 4 Tags Updated 1 year ago